© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107203
    Prev
    Next
    INDEX
    Explanations

    preliminary studies

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires most strongly on proper‐noun–style and metadata tokens—i.e. capitalized names, titles, license/version labels, and other document‐header or structured‐info keywords.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    だと思います
    -0.77
    atina
    -0.73
    чение
    -0.67
    وفاته
    -0.63
    imgur
    -0.62
    fgets
    -0.62
     Isles
    -0.61
    Burke
    -0.60
     Tung
    -0.60
    ключение
    -0.60
    POSITIVE LOGITS
     ramen
    0.69
    bró
    0.68
    Become
    0.67
     промежу
    0.67
     legacy
    0.66
    CCA
    0.66
    banen
    0.65
    łow
    0.65
    chante
    0.65
     boon
    0.64
    Activations Density 0.128%

    No Known Activations